Speech-to-Text
Accurate transcription built for Indian accents, dialects, and real-world audio with speaker diarisation.
Text-to-Speech
Natural, expressive voices across 11+ Indian languages for conversational AI, dubbing, and accessibility.
LLM
Multilingual large language model with native proficiency across Indian languages for text generation and reasoning.
Install Pipecat
pip install "pipecat-ai[daily,sarvam]" python-dotenv loguru
Add Sarvam API key
Set SARVAM_API_KEY in a .env file in your project directory
Build your pipeline
Use SarvamSTTService, SarvamLLMService, and SarvamTTSService in your pipeline
pip install "pipecat-ai[daily,sarvam]" python-dotenv logurufrom pipecat.services.sarvam.stt import SarvamSTTService from pipecat.services.sarvam.tts import SarvamTTSService from pipecat.services.sarvam.llm import SarvamLLMService stt = SarvamSTTService( api_key=os.getenv("SARVAM_API_KEY"), language="hi-IN", model="saaras:v3", mode="transcribe", ) tts = SarvamTTSService( api_key=os.getenv("SARVAM_API_KEY"), target_language_code="en-IN", model="bulbul:v3", speaker="shubh", ) llm = SarvamLLMService( api_key=os.getenv("SARVAM_API_KEY"), settings=SarvamLLMService.Settings(model="sarvam-105b"), ) pipeline = Pipeline([transport.input(), stt, llm, tts, transport.output()])
python agent.py
Runs the pipeline. With Daily transport, this creates a room and prints a URL. Open it in a browser to start talking to the agent.
IVR
IVR & Call Centres
Build conversational IVR systems with Indic-language understanding.
Voice
Voice Assistants
Create multimodal voice assistants with real-time streaming.
Rapid
Rapid Prototyping
Go from idea to working voice agent in under an hour.
Ready to build? Start building with Pipecat in minutes.
Ready to build?
Start building with Pipecat in minutes.